Amazon announced feature-level writes for Amazon SageMaker Feature Store via a new UpdateRecord API. Developers can now update one or more feature values in a single call without reading or rewriting the entire record. This streamlines feature management for teams using the managed repository to store, share, and manage ML features.
AWS published a case study describing how identity verification provider Jumio built a real-time feature store on AWS to support ML models that require sub-100ms latency. The architecture addresses challenges like data duplication, feature engineering, feature consistency, and manual deployment. The pattern applies to ML use cases needing real-time features.
AWS published a case study describing how identity verification provider Jumio built a real-time feature store on AWS to support ML models that require sub-100ms latency. The architecture addresses challenges like data duplication, feature engineering, feature consistency, and manual deployment. The pattern applies to ML use cases needing real-time features.
AWS announced Disaggregated Prefill and Decode (DPD) for LLM inference on SageMaker HyperPod, separating compute-bound prefill and memory-bound decode onto distinct GPU pools connected via EFA with RDMA. This eliminates interference where long prompts stall token generation for concurrent requests.
AWS announced Disaggregated Prefill and Decode (DPD) for LLM inference on SageMaker HyperPod, separating compute-bound prefill and memory-bound decode onto distinct GPU pools connected via EFA with RDMA. This eliminates interference where long prompts stall token generation for concurrent requests.
Amazon SageMaker AI introduced a user interface for its generative AI inference recommendations feature, which was previously available only via APIs. The UI helps developers quickly find optimal instance types, serving containers, and optimization strategies for deploying generative AI models, reducing the manual benchmarking cycle.
Amazon SageMaker AI introduced a user interface for its generative AI inference recommendations feature, which was previously available only via APIs. The UI helps developers quickly find optimal instance types, serving containers, and optimization strategies for deploying generative AI models, reducing the manual benchmarking cycle.
An AWS blog post explains how Managed MLflow on Amazon SageMaker AI automatically synchronizes models registered in MLflow into the SageMaker AI Model Registry. The workflow addresses the gap between experimentation, where data scientists track many candidate runs, and governance, where officers need one authoritative registry to validate, approve, and audit production-bound models.
An AWS blog post explains how Managed MLflow on Amazon SageMaker AI automatically synchronizes models registered in MLflow into the SageMaker AI Model Registry. The workflow addresses the gap between experimentation, where data scientists track many candidate runs, and governance, where officers need one authoritative registry to validate, approve, and audit production-bound models.
Amazon reported better-than-expected Q2 earnings with net sales up 20%, driven by cloud revenue. Investors sent stock up nearly 10% after hours, signaling approval of continued heavy data center spending. Amazon spent $173 billion on property and equipment in the fiscal year ending June 30, underscoring its commitment to AI infrastructure.
Amazon reported better-than-expected Q2 earnings with net sales up 20%, driven by cloud revenue. Investors sent stock up nearly 10% after hours, signaling approval of continued heavy data center spending. Amazon spent $173 billion on property and equipment in the fiscal year ending June 30, underscoring its commitment to AI infrastructure.